diff --git a/clang/lib/Basic/Targets/AMDGPU.cpp b/clang/lib/Basic/Targets/AMDGPU.cpp
--- a/clang/lib/Basic/Targets/AMDGPU.cpp
+++ b/clang/lib/Basic/Targets/AMDGPU.cpp
@@ -315,6 +315,8 @@
   if (hasFastFMA())
     Builder.defineMacro("FP_FAST_FMA");
 
+  Builder.defineMacro("__AMDGCN_WAVEFRONT_SIZE__", Twine(WavefrontSize));
+  // ToDo: deprecate this macro for naming consistency.
   Builder.defineMacro("__AMDGCN_WAVEFRONT_SIZE", Twine(WavefrontSize));
   Builder.defineMacro("__AMDGCN_CUMODE__", Twine(CUMode));
 }
diff --git a/clang/test/CodeGenHIP/maybe_undef-attr-verify.hip b/clang/test/CodeGenHIP/maybe_undef-attr-verify.hip
--- a/clang/test/CodeGenHIP/maybe_undef-attr-verify.hip
+++ b/clang/test/CodeGenHIP/maybe_undef-attr-verify.hip
@@ -20,7 +20,7 @@
 #define __maybe_undef __attribute__((maybe_undef))
 #define WARP_SIZE 64
 
-static constexpr int warpSize = __AMDGCN_WAVEFRONT_SIZE;
+static constexpr int warpSize = __AMDGCN_WAVEFRONT_SIZE__;
 
 __device__ static inline unsigned int __lane_id() {
     return  __builtin_amdgcn_mbcnt_hi(
diff --git a/clang/test/Driver/hip-macros.hip b/clang/test/Driver/hip-macros.hip
--- a/clang/test/Driver/hip-macros.hip
+++ b/clang/test/Driver/hip-macros.hip
@@ -17,6 +17,8 @@
 // RUN: %clang -E -dM --offload-arch=gfx1010 -mno-wavefrontsize64 \
 // RUN:   --cuda-device-only -nogpuinc -nogpulib \
 // RUN:   -mwavefrontsize64 %s 2>&1 | FileCheck --check-prefixes=WAVE64 %s
+// WAVE64-DAG: #define __AMDGCN_WAVEFRONT_SIZE__ 64
+// WAVE32-DAG: #define __AMDGCN_WAVEFRONT_SIZE__ 32
 // WAVE64-DAG: #define __AMDGCN_WAVEFRONT_SIZE 64
 // WAVE32-DAG: #define __AMDGCN_WAVEFRONT_SIZE 32